NeilBrown [Sat, 4 May 2019 10:24:56 +0000 (20:24 +1000)]
mmc: mtk-sd: don't hard-code interrupt trigger type
When using devicetree for configuration, interrupt trigger type
should be described in the dts file, not hard-coded in the C code.
The mtk-sd silicon in the mt7621 soc uses an active-high interrupt
and so cannot be used with the current code.
So replace IRQF_TRIGGER_LOW with IRQF_TRIGGER_NONE.
Also IRQF_ONESHOT is not needed - it is used for threaded interrupt
handlers, and this driver does not used a threaded interrupt handler.
So remove that setting.
Raul E Rangel [Thu, 2 May 2019 19:07:14 +0000 (13:07 -0600)]
mmc: core: Fix tag set memory leak
The tag set is allocated in mmc_init_queue but never freed. This results
in a memory leak. This change makes sure we free the tag set when the
queue is also freed.
mmc: mmci: Prevent polling for busy detection in IRQ context
The IRQ handler, mmci_irq(), loops until all status bits have been cleared.
However, the status bit signaling busy in variant->busy_detect_flag, may be
set even if busy detection isn't monitored for the current request.
This may be the case for the CMD11 when switching the I/O voltage, which
leads to that mmci_irq() busy loops in IRQ context. Fix this problem, by
clearing the status bit for busy, before continuing to validate the
condition for the loop. This is safe, because the busy status detection has
already been taken care of by mmci_cmd_irq().
mmc: usdhi6rol0: mark expected switch fall-throughs
In preparation to enabling -Wimplicit-fallthrough, mark switch
cases where we are expecting to fall through.
This patch fixes the following warnings:
In file included from drivers/mmc/host/usdhi6rol0.c:9:
drivers/mmc/host/usdhi6rol0.c: In function ‘usdhi6_timeout_work’:
./include/linux/device.h:1483:2: warning: this statement may fall through [-Wimplicit-fallthrough=]
_dev_err(dev, dev_fmt(fmt), ##__VA_ARGS__)
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
drivers/mmc/host/usdhi6rol0.c:1689:3: note: in expansion of macro ‘dev_err’
dev_err(mmc_dev(host->mmc), "Invalid state %u\n", host->wait);
^~~~~~~
drivers/mmc/host/usdhi6rol0.c:1691:2: note: here
case USDHI6_WAIT_FOR_CMD:
^~~~
drivers/mmc/host/usdhi6rol0.c:1711:3: warning: this statement may fall through [-Wimplicit-fallthrough=]
usdhi6_sg_unmap(host, true);
^~~~~~~~~~~~~~~~~~~~~~~~~~~
drivers/mmc/host/usdhi6rol0.c:1716:2: note: here
case USDHI6_WAIT_FOR_DATA_END:
^~~~
CC [M] drivers/isdn/hisax/hisax_isac.o
drivers/mmc/host/usdhi6rol0.c: In function ‘usdhi6_stop_cmd’:
drivers/mmc/host/usdhi6rol0.c:1338:6: warning: this statement may fall through [-Wimplicit-fallthrough=]
if (mrq->stop->opcode == MMC_STOP_TRANSMISSION) {
^
drivers/mmc/host/usdhi6rol0.c:1343:2: note: here
default:
^~~~~~~
Warning level 3 was used: -Wimplicit-fallthrough=3
This patch is part of the ongoing efforts to enable
-Wimplicit-fallthrough.
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com> Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
The SD Physical Layer Spec says the following: Since the SD Memory Card
shall support at least the two bus modes 1-bit or 4-bit width, then any SD
Card shall set at least bits 0 and 2 (SD_BUS_WIDTH="0101").
This change verifies the card has specified a bus width.
AMD SDHC Device 7806 can get into a bad state after a card disconnect
where anything transferred via the DATA lines will always result in a
zero filled buffer. Currently the driver will continue without error if
the HC is in this condition. A block device will be created, but reading
from it will result in a zero buffer. This makes it seem like the SD
device has been erased, when in actuality the data is never getting
copied from the DATA lines to the data buffer.
SCR is the first command in the SD initialization sequence that uses the
DATA lines. By checking that the response was invalid, we can abort
mounting the card.
mmc: sdhci-esdhc-imx: Add HS400 support for iMX7ULP
Add HS400 support for iMX7ULP B0.
According to IC suggest, need to clear the STROBE_DLL_CTRL_RESET
before any setting of STROBE_DLL_CTRL register.
USDHC has register bits(bit[27~20] of register STROBE_DLL_CTRL)
for slave sel value. If this register bits value is 0, it needs
256 ref_clk cycles to update slave sel value. IC suggest to set
bit[27~20] to 0x4, it only need 4 ref_clk cycle to update slave
sel value. This will short the lock time of slave.
i.MX7ULP B0 will need more time to lock the REF and SLV, so change
to add 5us delay.
mmc: sdhci-esdhc-imx: add pm_qos to interact with cpuidle
On some SoCs such as i.MX7ULP, there is no busfreq
driver, but cpuidle has some levels which may disable
system/bus clocks, so need to add pm_qos to prevent
cpuidle from entering low level idles and make sure
system/bus clocks are enabled when usdhc is active.
Use signal resampling tuning for the UHS and HS200 modes.
Instead of trying to get the *best* resampling setting with complex
window calculation, we just stop on the first working setting.
If the tuning setting later proves unstable, we will just continue the
tuning where we left it.
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com> Tested-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com> Reviewed-by: Kevin Hilman <khilman@baylibre.com> Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
This remove all the code related to phase settings. Using the Rx phase
for tuning has not been reliable. We had several issues over the past
months, on both v2 and v3 mmc chips After discussing the issue matter
with Amlogic, They suggested to set a phase shift of 180 between Core and
Tx and use signal resampling for the tuning.
Since we won't be playing with the phase anymore, let's remove all the
clock code related to it and set the appropriate value on init.
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com> Tested-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com> Reviewed-by: Kevin Hilman <khilman@baylibre.com> Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
mmc: meson-gx: avoid clock glitch when switching to DDR modes
Activating DDR in the Amlogic mmc controller, among other things, will
divide the output clock by 2. So by activating it with clock on, we are
creating a glitch on the output.
Instead, let's deal with DDR when the clock output is off, when setting
the clock.
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com> Tested-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com> Reviewed-by: Kevin Hilman <khilman@baylibre.com> Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
At the moment, all our attempts to enable HS400 on Amlogic chipsets have
been unsuccessful or unreliable. Until we can figure out how to enable this
mode safely and reliably, let's force it off.
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com> Acked-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com> Reviewed-by: Kevin Hilman <khilman@baylibre.com> Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
There is no reason for another device to request the MMC irq. It should
only be used the MMC device, so remove IRQ_SHARED and replace by
IRQ_ONESHOT as we don't the irq to fire again until the irq thread is
done
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com> Reviewed-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com> Reviewed-by: Kevin Hilman <khilman@baylibre.com> Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Daniel Drake [Mon, 29 Apr 2019 05:14:26 +0000 (13:14 +0800)]
mmc: alcor: work with multiple-entry sglists
DMA on this hardware is limited to dealing with a 4096 bytes at a
time. Previously, the driver was set up accordingly to request single-page
DMA buffers, however that had the effect of generating a large number
of small MMC requests for data I/O.
Improve the driver to accept multi-entry scatter-gather lists. The size of
each entry is already capped to 4096 bytes (AU6601_MAX_DMA_BLOCK_SIZE),
matching the hardware requirements. Existing driver code already iterates
through remaining sglist entries after each DMA transfer is complete.
Also add some comments to help clarify the situation, and clear up
some of the confusion I had regarding DMA vs PIO.
Testing with dd, this increases write performance from 2mb/sec to
10mb/sec, and increases read performance from 4mb/sec to 14mb/sec.
Usage of the DMA page iterator was problematic here because
we were not considering offset & length of entries in the scatterlist.
Also, after further discussion, the suggested revised approach is much
more similar to the driver implementation before this commit was
applied, so revert it.
Signed-off-by: Daniel Drake <drake@endlessm.com> Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
memstick: tifm: remove set but not used variable 'data'
Fixes gcc '-Wunused-but-set-variable' warning:
drivers/memstick/host/tifm_ms.c: In function 'tifm_ms_issue_cmd':
drivers/memstick/host/tifm_ms.c:259:17: warning:
variable 'data' set but not used [-Wunused-but-set-variable]
It's not used any more since commit 92b22d935fed ("tifm: fix the
MemoryStick host fifo handling code")
Pan Bian [Wed, 17 Apr 2019 08:28:37 +0000 (16:28 +0800)]
mmc: core: fix possible use after free of host
In the function mmc_alloc_host, the function put_device is called to
release allocated resources when mmc_gpio_alloc fails. Finally, the
function pointed by host->class_dev.class->dev_release (i.e.,
mmc_host_classdev_release) is used to release resources including the
host structure. However, after put_device, host is used and released
again. Resulting in a use-after-free bug.
Fixes: 1ed217194488 ("mmc: core: fix error path in mmc_host_alloc") Signed-off-by: Pan Bian <bianpan2016@163.com> Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
* pm-devfreq:
PM / devfreq: add tracing for scheduling work
trace: events: add devfreq trace event file
PM / devfreq: rk3399_dmc: Pass ODT and auto power down parameters to TF-A.
PM / devfreq: rockchip-dfi: Move GRF definitions to a common place.
PM / devfreq: exynos-bus: Suspend all devices on system shutdown
PM / devfreq: Fix static checker warning in try_then_request_governor
PM / devfreq: Restart previous governor if new governor fails to start
PM / devfreq: tegra: remove unneeded variable
PM / devfreq: rockchip-dfi: remove unneeded semicolon
PM / devfreq: rk3399_dmc: remove unneeded semicolon
PM / devfreq: consistent indentation
PM / devfreq: fix missing check of return value in devfreq_add_device()
PM / devfreq: fix mem leak in devfreq_add_device()
PM / devfreq: Use of_node_name_eq for node name comparisons
* pm-domains:
PM / Domains: Allow to attach a CPU via genpd_dev_pm_attach_by_id|name()
PM / Domains: Search for the CPU device outside the genpd lock
PM / Domains: Drop unused in-parameter to some genpd functions
PM / Domains: Use the base device for driver_deferred_probe_check_state()
PM / Domains: Enable genpd_dev_pm_attach_by_id|name() for single PM domain
PM / Domains: Allow OF lookup for multi PM domain case from ->attach_dev()
PM / Domains: Don't kfree() the virtual device in the error path
PM / Domains: remove unnecessary unlikely()
* pm-misc:
firmware/psci: add support for SYSTEM_RESET2
drivers: firmware: psci: Announce support for OS initiated suspend mode
drivers: firmware: psci: Simplify error path of psci_dt_init()
drivers: firmware: psci: Split psci_dt_cpu_init_idle()
MAINTAINERS: Update files for PSCI
drivers: firmware: psci: Move psci to separate directory
* pm-cpuidle:
PM / Domains: Add genpd governor for CPUs
cpuidle: Export the next timer expiration for CPUs
PM / Domains: Add support for CPU devices to genpd
PM / Domains: Add generic data pointer to struct genpd_power_state
cpuidle: exynos: Unify target residency for AFTR and coupled AFTR states
* pm-sleep:
PM / core: Propagate dev->power.wakeup_path when no callbacks
PM / core: Introduce dpm_async_fn() helper
PM / core: fix kerneldoc comment for device_pm_wait_for_dev()
PM / core: fix kerneldoc comment for dpm_watchdog_handler()
PM / sleep: Measure the time of filesystems syncing
PM / sleep: Refactor filesystems sync to reduce duplication
PM / wakeup: Use pm_pr_dbg() instead of pr_debug()
* acpi-doc: (25 commits)
Documentation: ACPI: move video_extension.txt to firmware-guide/acpi and convert to reST
Documentation: ACPI: move ssdt-overlays.txt to admin-guide/acpi and convert to reST
Documentation: ACPI: move lpit.txt to firmware-guide/acpi and convert to reST
Documentation: ACPI: move cppc_sysfs.txt to admin-guide/acpi and convert to reST
Documentation: ACPI: move apei/einj.txt to firmware-guide/acpi and convert to reST
Documentation: ACPI: move apei/output_format.txt to firmware-guide/acpi and convert to reST
Documentation: ACPI: move aml-debugger.txt to firmware-guide/acpi and convert to reST
Documentation: ACPI: move method-tracing.txt to firmware-guide/acpi and convert to rsST
Documentation: ACPI: move debug.txt to firmware-guide/acpi and convert to reST
Documentation: ACPI: move dsd/data-node-references.txt to firmware-guide/acpi and convert to reST
Documentation: ACPI: move dsd/graph.txt to firmware-guide/acpi and convert to reST
Documentation: ACPI: move acpi-lid.txt to firmware-guide/acpi and convert to reST
Documentation: ACPI: move i2c-muxes.txt to firmware-guide/acpi and convert to reST
Documentation: ACPI: move dsdt-override.txt to admin-guide/acpi and convert to reST
Documentation: ACPI: move initrd_table_override.txt to admin-guide/acpi and convert to reST
Documentation: ACPI: move method-customizing.txt to firmware-guide/acpi and convert to reST
Documentation: ACPI: move gpio-properties.txt to firmware-guide/acpi and convert to reST
Documentation: ACPI: move DSD-properties-rules.txt to firmware-guide/acpi and covert to reST
Documentation: ACPI: move scan_handlers.txt to driver-api/acpi and convert to reST
Documentation: ACPI: move linuxized-acpica.txt to driver-api/acpi and convert to reST
...
Merge branches 'acpi-utils', 'acpi-video', 'acpi-soc' and 'acpi-button'
* acpi-utils:
gpio: merrifield: Fix build err without CONFIG_ACPI
ACPI / utils: Remove deprecated function since no user left
ASoC: Intel: cht_bsw_rt5672: Convert to use acpi_dev_get_first_match_dev()
ASoC: Intel: cht_bsw_rt5645: Convert to use acpi_dev_get_first_match_dev()
ASoC: Intel: bytcr_rt5651: Convert to use acpi_dev_get_first_match_dev()
ASoC: Intel: bytcr_rt5640: Convert to use acpi_dev_get_first_match_dev()
ASoC: Intel: bytcht_es8316: Convert to use acpi_dev_get_first_match_dev()
ASoC: Intel: bytcht_da7213: Convert to use acpi_dev_get_first_match_dev()
gpio: merrifield: Convert to use acpi_dev_get_first_match_dev()
extcon: axp288: Convert to use acpi_dev_get_first_match_dev()
ACPI / utils: Introduce acpi_dev_get_first_match_dev() helper
* acpi-video:
ACPI: video: Use vendor backlight on Sony VPCEH3U1E
* acpi-soc:
ACPI / LPSS: Use acpi_lpss_* instead of acpi_subsys_* functions for hibernate
* acpi-button:
ACPI: button: reinitialize button state upon resume
* acpica:
ACPICA: Update version to 20190405
ACPICA: Namespace: add check to avoid null pointer dereference
ACPICA: Update version to 20190329
ACPICA: utilities: fix spelling of PCC to platform_comm_channel
ACPICA: Rename nameseg length macro/define for clarity
ACPICA: Rename nameseg compare macro for clarity
ACPICA: Rename nameseg copy macro for clarity
x86/fpu: Fault-in user stack if copy_fpstate_to_sigframe() fails
In the compacted form, XSAVES may save only the XMM+SSE state but skip
FP (x87 state).
This is denoted by header->xfeatures = 6. The fastpath
(copy_fpregs_to_sigframe()) does that but _also_ initialises the FP
state (cwd to 0x37f, mxcsr as we do, remaining fields to 0).
The slowpath (copy_xstate_to_user()) leaves most of the FP
state untouched. Only mxcsr and mxcsr_flags are set due to
xfeatures_mxcsr_quirk(). Now that XFEATURE_MASK_FP is set
unconditionally, see
04944b793e18 ("x86: xsave: set FP, SSE bits in the xsave header in the user sigcontext"),
on return from the signal, random garbage is loaded as the FP state.
Instead of utilizing copy_xstate_to_user(), fault-in the user memory
and retry the fast path. Ideally, the fast path succeeds on the second
attempt but may be retried again if the memory is swapped out due
to memory pressure. If the user memory can not be faulted-in then
get_user_pages() returns an error so we don't loop forever.
Fault in memory via get_user_pages_unlocked() so
copy_fpregs_to_sigframe() succeeds without a fault.
Fixes: 69277c98f5eef ("x86/fpu: Always store the registers in copy_fpstate_to_sigframe()") Reported-by: Kurt Kanzenbach <kurt.kanzenbach@linutronix.de> Suggested-by: Dave Hansen <dave.hansen@intel.com> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Borislav Petkov <bp@suse.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Dave Hansen <dave.hansen@intel.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jann Horn <jannh@google.com> Cc: "linux-mm@kvack.org" <linux-mm@kvack.org> Cc: Qian Cai <cai@lca.pw> Cc: Rik van Riel <riel@surriel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: x86-ml <x86@kernel.org> Link: https://lkml.kernel.org/r/20190502171139.mqtegctsg35cir2e@linutronix.de
Dan Carpenter [Tue, 23 Apr 2019 10:40:20 +0000 (13:40 +0300)]
i3c: Fix a shift wrap bug in i3c_bus_set_addr_slot_status()
The problem here is that addr can be I3C_BROADCAST_ADDR (126). That
means we're shifting by (126 * 2) % 64 which is 60. The
I3C_ADDR_SLOT_STATUS_MASK is an enum which is an unsigned int in GCC
so shifts greater than 31 are undefined.
Fixes: 3a379bbcea0a ("i3c: Add core I3C infrastructure") Cc: <stable@vger.kernel.org> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Helge Deller [Sun, 5 May 2019 21:54:34 +0000 (23:54 +0200)]
parisc: Rename LEVEL to PA_ASM_LEVEL to avoid name clash with DRBD code
LEVEL is a very common word, and now after many years it suddenly
clashed with another LEVEL define in the DRBD code.
Rename it to PA_ASM_LEVEL instead.
Linus Torvalds [Sun, 5 May 2019 21:37:25 +0000 (14:37 -0700)]
Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf fixes from Ingo Molnar:
"I'd like to apologize for this very late pull request: I was dithering
through the week whether to send the fixes, and then yesterday Jiri's
crash fix for a regression introduced in this cycle clearly marked
perf/urgent as 'must merge now'.
Most of the commits are tooling fixes, plus there's three kernel fixes
via four commits:
- race fix in the Intel PEBS code
- fix an AUX bug and roll back a previous attempt
- fix AMD family 17h generic HW cache-event perf counters
The largest diffstat contribution comes from the AMD fix - a new event
table is introduced, which is a fairly low risk change but has a large
linecount"
* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
perf/x86/intel: Fix race in intel_pmu_disable_event()
perf/x86/intel/pt: Remove software double buffering PMU capability
perf/ring_buffer: Fix AUX software double buffering
perf tools: Remove needless asm/unistd.h include fixing build in some places
tools arch uapi: Copy missing unistd.h headers for arc, hexagon and riscv
tools build: Add -ldl to the disassembler-four-args feature test
perf cs-etm: Always allocate memory for cs_etm_queue::prev_packet
perf cs-etm: Don't check cs_etm_queue::prev_packet validity
perf report: Report OOM in status line in the GTK UI
perf bench numa: Add define for RUSAGE_THREAD if not present
tools lib traceevent: Change tag string for error
perf annotate: Fix build on 32 bit for BPF annotation
tools uapi x86: Sync vmx.h with the kernel
perf bpf: Return value with unlocking in perf_env__find_btf()
MAINTAINERS: Include vendor specific files under arch/*/events/*
perf/x86/amd: Update generic hardware cache events for Family 17h
Linus Torvalds [Sun, 5 May 2019 21:26:11 +0000 (14:26 -0700)]
Merge branch 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 fix from Ingo Molnar:
"Disable function tracing during early SME setup to fix a boot crash on
SME-enabled kernels running distro kernels (some of which have
function tracing enabled)"
* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/mm/mem_encrypt: Disable all instrumentation for early SME setup
Nadav Amit [Sun, 5 May 2019 01:11:24 +0000 (18:11 -0700)]
x86/mm: Initialize PGD cache during mm initialization
Poking-mm initialization might require to duplicate the PGD in early
stage. Initialize the PGD cache earlier to prevent boot failures.
Reported-by: kernel test robot <lkp@intel.com> Signed-off-by: Nadav Amit <namit@vmware.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rick Edgecombe <rick.p.edgecombe@intel.com> Cc: Rik van Riel <riel@surriel.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Thomas Gleixner <tglx@linutronix.de> Fixes: 4fc19708b165 ("x86/alternatives: Initialize temporary mm for patching") Link: http://lkml.kernel.org/r/20190505011124.39692-1-namit@vmware.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
Linus Torvalds [Sun, 5 May 2019 16:28:45 +0000 (09:28 -0700)]
Merge branch 'fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs
Pull vfs fixes from Al Viro:
- a couple of ->i_link use-after-free fixes
- regression fix for wrong errno on absent device name in mount(2)
(this cycle stuff)
- ancient UFS braino in large GID handling on Solaris UFS images (bogus
cut'n'paste from large UID handling; wrong field checked to decide
whether we should look at old (16bit) or new (32bit) field)
* 'fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
ufs: fix braino in ufs_get_inode_gid() for solaris UFS flavour
Abort file_remove_privs() for non-reg. files
[fix] get rid of checking for absent device name in vfs_get_tree()
apparmorfs: fix use-after-free on symlink traversal
securityfs: fix use-after-free on symlink traversal
Jiri Olsa [Sat, 4 May 2019 15:15:56 +0000 (17:15 +0200)]
perf/x86/intel: Fix race in intel_pmu_disable_event()
New race in x86_pmu_stop() was introduced by replacing the
atomic __test_and_clear_bit() of cpuc->active_mask by separate
test_bit() and __clear_bit() calls in the following commit:
3966c3feca3f ("x86/perf/amd: Remove need to check "running" bit in NMI handler")
The race causes panic for PEBS events with enabled callchains:
The event is configured to make samples from PEBS drain code,
but when it's disabled, we'll go through NMI path instead,
where data->callchain will not get allocated and we'll crash:
Ming Lei [Tue, 30 Apr 2019 01:52:29 +0000 (09:52 +0800)]
block: don't drain in-progress dispatch in blk_cleanup_queue()
Now freeing hw queue resource is moved to hctx's release handler,
we don't need to worry about the race between blk_cleanup_queue and
run queue any more.
So don't drain in-progress dispatch in blk_cleanup_queue().
This is basically revert of c2856ae2f315 ("blk-mq: quiesce queue before
freeing queue").
Cc: Dongli Zhang <dongli.zhang@oracle.com> Cc: James Smart <james.smart@broadcom.com> Cc: Bart Van Assche <bart.vanassche@wdc.com> Cc: linux-scsi@vger.kernel.org, Cc: Martin K . Petersen <martin.petersen@oracle.com>, Cc: Christoph Hellwig <hch@lst.de>, Cc: James E . J . Bottomley <jejb@linux.vnet.ibm.com>, Reviewed-by: Bart Van Assche <bvanassche@acm.org> Reviewed-by: Hannes Reinecke <hare@suse.com> Tested-by: James Smart <james.smart@broadcom.com> Signed-off-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
Ming Lei [Tue, 30 Apr 2019 01:52:28 +0000 (09:52 +0800)]
blk-mq: move cancel of hctx->run_work into blk_mq_hw_sysfs_release
hctx is always released after requeue is freed.
With holding queue's kobject refcount, it is safe for driver to run queue,
so one run queue might be scheduled after blk_sync_queue() is done.
So moving the cancel of hctx->run_work into blk_mq_hw_sysfs_release()
for avoiding run released queue.
Cc: Dongli Zhang <dongli.zhang@oracle.com> Cc: James Smart <james.smart@broadcom.com> Cc: Bart Van Assche <bart.vanassche@wdc.com> Cc: linux-scsi@vger.kernel.org, Cc: Martin K . Petersen <martin.petersen@oracle.com>, Cc: Christoph Hellwig <hch@lst.de>, Cc: James E . J . Bottomley <jejb@linux.vnet.ibm.com>, Reviewed-by: Bart Van Assche <bvanassche@acm.org> Reviewed-by: Hannes Reinecke <hare@suse.com> Tested-by: James Smart <james.smart@broadcom.com> Signed-off-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
Ming Lei [Tue, 30 Apr 2019 01:52:27 +0000 (09:52 +0800)]
blk-mq: always free hctx after request queue is freed
In normal queue cleanup path, hctx is released after request queue
is freed, see blk_mq_release().
However, in __blk_mq_update_nr_hw_queues(), hctx may be freed because
of hw queues shrinking. This way is easy to cause use-after-free,
because: one implicit rule is that it is safe to call almost all block
layer APIs if the request queue is alive; and one hctx may be retrieved
by one API, then the hctx can be freed by blk_mq_update_nr_hw_queues();
finally use-after-free is triggered.
Fixes this issue by always freeing hctx after releasing request queue.
If some hctxs are removed in blk_mq_update_nr_hw_queues(), introduce
a per-queue list to hold them, then try to resuse these hctxs if numa
node is matched.
Cc: Dongli Zhang <dongli.zhang@oracle.com> Cc: James Smart <james.smart@broadcom.com> Cc: Bart Van Assche <bart.vanassche@wdc.com> Cc: linux-scsi@vger.kernel.org, Cc: Martin K . Petersen <martin.petersen@oracle.com>, Cc: Christoph Hellwig <hch@lst.de>, Cc: James E . J . Bottomley <jejb@linux.vnet.ibm.com>, Reviewed-by: Hannes Reinecke <hare@suse.com> Tested-by: James Smart <james.smart@broadcom.com> Signed-off-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
Ming Lei [Tue, 30 Apr 2019 01:52:26 +0000 (09:52 +0800)]
blk-mq: split blk_mq_alloc_and_init_hctx into two parts
Split blk_mq_alloc_and_init_hctx into two parts, and one is
blk_mq_alloc_hctx() for allocating all hctx resources, another
is blk_mq_init_hctx() for initializing hctx, which serves as
counter-part of blk_mq_exit_hctx().
Cc: Dongli Zhang <dongli.zhang@oracle.com> Cc: James Smart <james.smart@broadcom.com> Cc: Bart Van Assche <bart.vanassche@wdc.com> Cc: linux-scsi@vger.kernel.org Cc: Martin K . Petersen <martin.petersen@oracle.com> Cc: Christoph Hellwig <hch@lst.de> Cc: James E . J . Bottomley <jejb@linux.vnet.ibm.com> Reviewed-by: Hannes Reinecke <hare@suse.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Tested-by: James Smart <james.smart@broadcom.com> Signed-off-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
Ming Lei [Tue, 30 Apr 2019 01:52:25 +0000 (09:52 +0800)]
blk-mq: free hw queue's resource in hctx's release handler
Once blk_cleanup_queue() returns, tags shouldn't be used any more,
because blk_mq_free_tag_set() may be called. Commit 45a9c9d909b2
("blk-mq: Fix a use-after-free") fixes this issue exactly.
However, that commit introduces another issue. Before 45a9c9d909b2,
we are allowed to run queue during cleaning up queue if the queue's
kobj refcount is held. After that commit, queue can't be run during
queue cleaning up, otherwise oops can be triggered easily because
some fields of hctx are freed by blk_mq_free_queue() in blk_cleanup_queue().
We have invented ways for addressing this kind of issue before, such as:
8dc765d438f1 ("SCSI: fix queue cleanup race before queue initialization is done") c2856ae2f315 ("blk-mq: quiesce queue before freeing queue")
But still can't cover all cases, recently James reports another such
kind of issue:
This issue can be quite hard to address by previous way, given
scsi_run_queue() may run requeues for other LUNs.
Fixes the above issue by freeing hctx's resources in its release handler, and this
way is safe becasue tags isn't needed for freeing such hctx resource.
This approach follows typical design pattern wrt. kobject's release handler.
Cc: Dongli Zhang <dongli.zhang@oracle.com> Cc: James Smart <james.smart@broadcom.com> Cc: Bart Van Assche <bart.vanassche@wdc.com> Cc: linux-scsi@vger.kernel.org, Cc: Martin K . Petersen <martin.petersen@oracle.com>, Cc: Christoph Hellwig <hch@lst.de>, Cc: James E . J . Bottomley <jejb@linux.vnet.ibm.com>, Reported-by: James Smart <james.smart@broadcom.com> Fixes: 45a9c9d909b2 ("blk-mq: Fix a use-after-free") Cc: stable@vger.kernel.org Reviewed-by: Hannes Reinecke <hare@suse.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Tested-by: James Smart <james.smart@broadcom.com> Signed-off-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
Ming Lei [Tue, 30 Apr 2019 01:52:24 +0000 (09:52 +0800)]
blk-mq: move cancel of requeue_work into blk_mq_release
With holding queue's kobject refcount, it is safe for driver
to schedule requeue. However, blk_mq_kick_requeue_list() may
be called after blk_sync_queue() is done because of concurrent
requeue activities, then requeue work may not be completed when
freeing queue, and kernel oops is triggered.
So moving the cancel of requeue_work into blk_mq_release() for
avoiding race between requeue and freeing queue.
Cc: Dongli Zhang <dongli.zhang@oracle.com> Cc: James Smart <james.smart@broadcom.com> Cc: Bart Van Assche <bart.vanassche@wdc.com> Cc: linux-scsi@vger.kernel.org, Cc: Martin K . Petersen <martin.petersen@oracle.com>, Cc: Christoph Hellwig <hch@lst.de>, Cc: James E . J . Bottomley <jejb@linux.vnet.ibm.com>, Reviewed-by: Bart Van Assche <bvanassche@acm.org> Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de> Reviewed-by: Hannes Reinecke <hare@suse.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Tested-by: James Smart <james.smart@broadcom.com> Signed-off-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
Ming Lei [Tue, 30 Apr 2019 01:52:23 +0000 (09:52 +0800)]
blk-mq: grab .q_usage_counter when queuing request from plug code path
Just like aio/io_uring, we need to grab 2 refcount for queuing one
request, one is for submission, another is for completion.
If the request isn't queued from plug code path, the refcount grabbed
in generic_make_request() serves for submission. In theroy, this
refcount should have been released after the sumission(async run queue)
is done. blk_freeze_queue() works with blk_sync_queue() together
for avoiding race between cleanup queue and IO submission, given async
run queue activities are canceled because hctx->run_work is scheduled with
the refcount held, so it is fine to not hold the refcount when
running the run queue work function for dispatch IO.
However, if request is staggered into plug list, and finally queued
from plug code path, the refcount in submission side is actually missed.
And we may start to run queue after queue is removed because the queue's
kobject refcount isn't guaranteed to be grabbed in flushing plug list
context, then kernel oops is triggered, see the following race:
blk_mq_flush_plug_list():
blk_mq_sched_insert_requests()
insert requests to sw queue or scheduler queue
blk_mq_run_hw_queue
Because of concurrent run queue, all requests inserted above may be
completed before calling the above blk_mq_run_hw_queue. Then queue can
be freed during the above blk_mq_run_hw_queue().
Fixes the issue by grab .q_usage_counter before calling
blk_mq_sched_insert_requests() in blk_mq_flush_plug_list(). This way is
safe because the queue is absolutely alive before inserting request.
Cc: Dongli Zhang <dongli.zhang@oracle.com> Cc: James Smart <james.smart@broadcom.com> Cc: linux-scsi@vger.kernel.org, Cc: Martin K . Petersen <martin.petersen@oracle.com>, Cc: Christoph Hellwig <hch@lst.de>, Cc: James E . J . Bottomley <jejb@linux.vnet.ibm.com>, Reviewed-by: Bart Van Assche <bvanassche@acm.org> Tested-by: James Smart <james.smart@broadcom.com> Signed-off-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
Linus Torvalds [Fri, 3 May 2019 23:49:46 +0000 (16:49 -0700)]
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm
Pull KVM fixes from Paolo Bonzini:
- PPC and ARM bugfixes from submaintainers
- Fix old Windows versions on AMD (recent regression)
- Fix old Linux versions on processors without EPT
- Fixes for LAPIC timer optimizations
* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (21 commits)
KVM: nVMX: Fix size checks in vmx_set_nested_state
KVM: selftests: make hyperv_cpuid test pass on AMD
KVM: lapic: Check for in-kernel LAPIC before deferencing apic pointer
KVM: fix KVM_CLEAR_DIRTY_LOG for memory slots of unaligned size
x86/kvm/mmu: reset MMU context when 32-bit guest switches PAE
KVM: x86: Whitelist port 0x7e for pre-incrementing %rip
Documentation: kvm: fix dirty log ioctl arch lists
KVM: VMX: Move RSB stuffing to before the first RET after VM-Exit
KVM: arm/arm64: Don't emulate virtual timers on userspace ioctls
kvm: arm: Skip stage2 huge mappings for unaligned ipa backed by THP
KVM: arm/arm64: Ensure vcpu target is unset on reset failure
KVM: lapic: Convert guest TSC to host time domain if necessary
KVM: lapic: Allow user to disable adaptive tuning of timer advancement
KVM: lapic: Track lapic timer advance per vCPU
KVM: lapic: Disable timer advancement if adaptive tuning goes haywire
x86: kvm: hyper-v: deal with buggy TLB flush requests from WS2012
KVM: x86: Consider LAPIC TSC-Deadline timer expired if deadline too short
KVM: PPC: Book3S: Protect memslots while validating user address
KVM: PPC: Book3S HV: Perserve PSSCR FAKE_SUSPEND bit on guest exit
KVM: arm/arm64: vgic-v3: Retire pending interrupts on disabling LPIs
...
parisc: Update huge TLB page support to use per-pagetable spinlock
This patch updates the parisc huge TLB page support to use per-pagetable spinlocks.
This patch requires Mikulas' per-pagetable spinlock patch and the revised TLB
serialization patch from Helge and myself. With Mikulas' patch, we need to use
the per-pagetable spinlock for page table updates. The TLB lock is only used
to serialize TLB flushes on machines with the Merced bus.
Signed-off-by: John David Anglin <dave.anglin@bell.net> Signed-off-by: Helge Deller <deller@gmx.de>
PA-RISC uses a global spinlock to protect pagetable updates in the TLB
fault handlers. When multiple cores are taking TLB faults simultaneously,
the cache line containing the spinlock becomes a bottleneck.
This patch embeds the spinlock in the top level page directory, so that
every process has its own lock. It improves performance by 30% when
doing parallel compilations.
At least on the N class systems, only one PxTLB inter processor
broadcast can be active at any one time on the Merced bus. If a Merced
bus is found, this patch serializes the TLB flushes with the
pa_tlb_flush_lock spinlock.
v1: Initial patch by Mikulas
v2: Added Merced detection by Helge
v3: Revised TLB serialization by Dave & Helge
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> Signed-off-by: John David Anglin <dave.anglin@bell.net> Signed-off-by: Helge Deller <deller@gmx.de>
Helge Deller [Wed, 1 May 2019 12:59:58 +0000 (14:59 +0200)]
parisc: Allow live-patching of __meminit functions
When making the text sections writeable with set_kernel_text_rw(1),
include all text sections including those in the __init section.
Otherwise functions marked with __meminit will stay read-only.
The pdtlb and pitlb instructions are strongly ordered. The asms invoking
these instructions should be compiler memory barriers to ensure the
compiler doesn't reorder memory operations around these instructions.
Signed-off-by: John David Anglin <dave.anglin@bell.net> CC: stable@vger.kernel.org # v4.20+ Fixes: 3847dab77421 ("parisc: Add alternative coding infrastructure") Signed-off-by: Helge Deller <deller@gmx.de>
parisc: Use ldcw instruction for SMP spinlock release barrier
There are only a couple of instructions that can function as a memory
barrier on parisc. Currently, we use the sync instruction as a memory
barrier when releasing a spinlock. However, the ldcw instruction is a
better barrier when we have a handy memory location since it operates in
the cache on coherent machines.
This patch updates the spinlock release code to use ldcw. I also
changed the "stw,ma" instructions to "stw" instructions as it is not an
adequate barrier.
Signed-off-by: John David Anglin <dave.anglin@bell.net> Signed-off-by: Helge Deller <deller@gmx.de>
parisc: Remove lock code to serialize TLB operations in pacache.S
TLB operations only need to be serialized on machines with the Merced
(Stretch) bus. The only machines in this category are L and N class, and
they require a 64-bit PA 2.0 kernel. On these machines, we use local TLB
purges in the tmpalias routines.
We don't need to serialize TLB purges on all other machines. Thus, the
lock/unlock code can be removed when CONFIG_PA20 is not defined.
Further, when CONFIG_PA20 is not defined, alternative patching converts
the TLB purges to local purges when PA 2.0 hardware has been detected.
Signed-off-by: John David Anglin <dave.anglin@bell.net> Tested-By: Sven Schnelle <svens@stackframe.org> Signed-off-by: Helge Deller <deller@gmx.de>
The commit 1c30844d2dfe ("mm: reclaim small amounts of memory when an
external fragmentation event occurs") breaks memory management on a
parisc c8000 workstation with this memory layout:
0) Start 0x0000000000000000 End 0x000000003fffffff Size 1024 MB
1) Start 0x0000000100000000 End 0x00000001bfdfffff Size 3070 MB
2) Start 0x0000004040000000 End 0x00000040ffffffff Size 3072 MB
With the patch 1c30844d2dfe, the kernel will incorrectly reclaim the
first zone when it fills up, ignoring the fact that there are two
completely free zones. Basiscally, it limits cache size to 1GiB.
The parisc kernel is currently using the DISCONTIGMEM implementation,
but isn't NUMA. Avoid this issue or strange work-arounds by switching to
the more commonly used SPARSEMEM implementation.
Reported-by: Mikulas Patocka <mpatocka@redhat.com> Fixes: 1c30844d2dfe ("mm: reclaim small amounts of memory when an external fragmentation event occurs") Signed-off-by: Helge Deller <deller@gmx.de>
Sven Schnelle [Thu, 18 Apr 2019 09:33:13 +0000 (11:33 +0200)]
parisc: enable wide mode early
The idle task might have been allocated above 4GB. With the current code
we cannot access that memory because the CPU is still running in narrow
mode.
This was found on a J5000 machine and the patch is required to enable
SPARSEMEM on that machine.
Signed-off-by: Sven Schnelle <svens@stackframe.org> Signed-off-by: Helge Deller <deller@gmx.de>
Sven Schnelle [Thu, 4 Apr 2019 19:14:09 +0000 (21:14 +0200)]
parisc: add parisc code patching
Instead of re-mapping the whole kernel text with RWX rights
add a patch_text() which can be used to replace instructions
in the kernel .text section. Based on the ARM implementation.
Signed-off-by: Sven Schnelle <svens@stackframe.org> Signed-off-by: Helge Deller <deller@gmx.de>
Petr Mladek [Fri, 3 May 2019 13:26:24 +0000 (15:26 +0200)]
livepatch: Remove custom kobject state handling
kobject_init() always succeeds and sets the reference count to 1.
It allows to always free the structures via kobject_put() and
the related release callback.
Note that the custom kobject state handling was used only
because we did not know that kobject_put() can and actually
should get called even when kobject_init_and_add() fails.
The patch should not change the existing behavior.
Suggested-by: "Tobin C. Harding" <tobin@kernel.org> Signed-off-by: Petr Mladek <pmladek@suse.com> Reviewed-by: Kamalesh Babulal <kamalesh@linux.vnet.ibm.com> Acked-by: Joe Lawrence <joe.lawrence@redhat.com> Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Linus Torvalds [Fri, 3 May 2019 18:42:01 +0000 (11:42 -0700)]
Merge branch 'i2c/for-current-fixed' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/wsa/linux
Pull i2c fixes from Wolfram Sang:
"I2C driver bugfixes and a MAINTAINERS update for you"
* 'i2c/for-current-fixed' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/wsa/linux:
i2c: Prevent runtime suspend of adapter when Host Notify is required
i2c: synquacer: fix enumeration of slave devices
MAINTAINERS: friendly takeover of i2c-gpio driver
i2c: designware: ratelimit 'transfer when suspended' errors
i2c: imx: correct the method of getting private data in notifier_call
Nicholas Piggin [Thu, 11 Apr 2019 03:34:48 +0000 (13:34 +1000)]
nohz_full: Allow the boot CPU to be nohz_full
Allow the boot CPU/CPU0 to be nohz_full. Have the boot CPU take the
do_timer duty during boot until a housekeeping CPU can take over.
This is supported when CONFIG_PM_SLEEP_SMP is not configured, or when
it is configured and the arch allows suspend on non-zero CPUs.
nohz_full has been trialed at a large supercomputer site and found to
significantly reduce jitter. In order to deploy it in production, they
need CPU0 to be nohz_full because their job control system requires
the application CPUs to start from 0, and the housekeeping CPUs are
placed higher. An equivalent job scheduling that uses CPU0 for
housekeeping could be achieved by modifying their system, but it is
preferable if nohz_full can support their environment without
modification.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rafael J . Wysocki <rafael.j.wysocki@intel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linuxppc-dev@lists.ozlabs.org Link: https://lkml.kernel.org/r/20190411033448.20842-6-npiggin@gmail.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
Nicholas Piggin [Thu, 11 Apr 2019 03:34:47 +0000 (13:34 +1000)]
sched/isolation: Require a present CPU in housekeeping mask
During housekeeping mask setup, currently a possible CPU is required.
That does not guarantee the CPU would be available at boot time, so
check to ensure that at least one present CPU is in the mask.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rafael J . Wysocki <rafael.j.wysocki@intel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linuxppc-dev@lists.ozlabs.org Link: https://lkml.kernel.org/r/20190411033448.20842-5-npiggin@gmail.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
Nicholas Piggin [Thu, 11 Apr 2019 03:34:46 +0000 (13:34 +1000)]
kernel/cpu: Allow non-zero CPU to be primary for suspend / kexec freeze
This patch provides an arch option, ARCH_SUSPEND_NONZERO_CPU, to
opt-in to allowing suspend to occur on one of the housekeeping CPUs
rather than hardcoded CPU0.
This will allow CPU0 to be a nohz_full CPU with a later change.
It may be possible for platforms with hardware/firmware restrictions
on suspend/wake effectively support this by handing off the final
stage to CPU0 when kernel housekeeping is no longer required. Another
option is to make housekeeping / nohz_full mask dynamic at runtime,
but the complexity could not be justified at this time.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rafael J . Wysocki <rafael.j.wysocki@intel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linuxppc-dev@lists.ozlabs.org Link: https://lkml.kernel.org/r/20190411033448.20842-4-npiggin@gmail.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
Nicholas Piggin [Thu, 11 Apr 2019 03:34:45 +0000 (13:34 +1000)]
power/suspend: Add function to disable secondaries for suspend
This adds a function to disable secondary CPUs for suspend that are
not necessarily non-zero / non-boot CPUs. Platforms will be able to
use this to suspend using non-zero CPUs.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rafael J . Wysocki <rafael.j.wysocki@intel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linuxppc-dev@lists.ozlabs.org Link: https://lkml.kernel.org/r/20190411033448.20842-3-npiggin@gmail.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
Now that we have a way to switch between MSC buffer windows, add code to
track the current window. The hardware register NWSA that contains the
address of the next window is unfortunately not always usable, and since
the driver has full control of the window switching, there is no reason
not to keep this on the software side.
Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Add support for asserting window switch trigger when tracing to MSU output
ports. This allows for software controlled switching between windows of
the MSU buffer, which can be used for double buffering while exporting the
trace data further from the MSU.
Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The trace enable/disable functions of the GTH include the code that starts
and stops trace flom from the sources. This start/stop functionality will
also be used in the window switch trigger sequence.
Factor out start/stop code from the larger trace enable/disable code in
preparation for the window switch sequence.
Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The code that waits for the pipeline empty condition of the MSU is
currently called in the path that disables the trace. We will also
need this in the window switch trigger sequence. Therefore, factor
out this code and make it accessible to the GTH device.
Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Instead of using a home-grown array of pointers to the DMA pages, switch
over to scatterlist data types and accessors, which has all the convenient
accessors, can be used to batch-map DMA memory and is convenient for
passing around between different layers, which will be useful when MSU
buffer management has to cross the boundaries of the MSU driver.
Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The only type of IRQ triggering event that is useful to us at the moment
is the "last block" interrupt of the MSU. This interrupt can only be
enabled via "MINTCTL" register that doesn't exist in earlier version of
the Intel TH.
Enumerate the presence of MINTCTL via per-device driver data structure
and only instantiate the IRQ resource for subdevices if this capability
is present.
Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
We intend to use the interrupt to detect Last Block condition in the MSU
driver, which we can use for double-buffering software-managed data
transfers.
Add an interrupt handler to the MSU driver.
Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Since Intel TH is capable of MSI interrupt signalling, make use of it.
The way it works is, each of the 7 interrupt triggering events has its
own vector in this mode, as opposed to interrupt line delivery, where
all events are signalled via the same line. Failing to enable MSI, the
driver falls back to using an interrupt line.
Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>